Neuron Explorer

Qwen3-0.6B

'and' joining parallel objects

A neuron in layer 15 of Qwen3-0.6B. Its strongest snippets are very consistent: they mostly peak on the same token. It is featured, so it has steering outputs.

What this neuron does

This neuron lights up on the word 'and' or 'or' when it links two things that share the same role, such as 'understanding of and applying' or 'control of and manage'. When it was turned up, the model's text became repetitive and drifted off topic, so the steering showed no clear theme.

Written by Claude from this neuron's activations and steering outputs. Confidence: medium. Think it is wrong? Flag it (opens a prefilled issue on GitHub).

Fires most on

The text windows where this neuron's activation was highest. Amber marks positive activation; the outlined token is the peak. Hover a token for its strength.

  1. #1 peak

    Mudejar at practically all levels of the economy, and the quotidian mingling of Muslim and Christian in field, workshop, and marketplace provided the foundation of—and the most effective adhesive reinforcing—the structure of Valencia's plural society. A common pre

  2. #2 peak

    time should focus on four critical areas: (1) developing understanding of and applying proportional relationships; (2) developing understanding of operations with rational numbers and working

  3. #3 peak

    /conflicts are most familiar to them.⏎Do the standards support students’ engagement in ongoing self-examination to excavate how one’s identities inform their understandings of and experiences with complex social problems (Mitchell, 20

  4. #4 peak

    the average volume of Internet traffic has historically grown by 40–50% per year. This growth leads to the growth of the transit fees paid by and paid to the upstream ISPs.⏎For example, while the price for Internet Transit drops

  5. #5 peak

    to protect millions of acres of forest and keep millions of tons of CO2 in the ground.⏎Our grants support organizations and communities that are working to regain control of and sustainably manage their traditional territories through land title initiatives, community education, development of

  6. #6 peak

    did not get any education on that part of their country and it hardly ever surfaces as part of the political discussion. Despite the active participation of Nubians in and before the revolution; their efforts to highlight their cause and their history of discrimination,

Steering

Push this neuron up or down while the model writes, and watch what changes. The outputs were generated ahead of time, so nothing runs in your browser.

turned down a lot
Prompt

Here is something I have been thinking about lately: if you don't think about the other side in the "other" side of the mind and you are thinking only about your own, you are not thinking. This is the theory of the "mind of the self and the mind of the

Most negative on

Where the activation went furthest below zero. Blue marks negative activation. Many neurons mean something different in each direction.

  1. #1 peak

    ⏎- A pair of matching socks⏎- Something that is soft⏎- Something that is round⏎- A photo of someone you love⏎- Something you love to play with<|endoftext|>The report’s focus is on perceptions of changes among pastoralists and

  2. #2 peak

    photograph of our fascinating universe is featured, along with a brief explanation written by a professional astronomer.⏎2013 May 19⏎Explanation: What on Earth is that? The Richat Structure in the Sahara Desert of Mauritania is

  3. #3 peak

    , a person’s views, or their behavior, all of which are not within your control? Is there a power struggle in the making? What exactly is triggering to you? When you’re aware of it, you can decide how to handle it

  4. #4 peak

    the adherent to a religion is necessarily, from the scholastic point of view, the proper person to speak for the religion. They go on to characterize as a "tightrope between academic and religious worlds of value" the situation of

Connections

Show on map

Which neurons in earlier layers feed this one, and which later ones it feeds. Amber links excite, blue links suppress; longer bars are stronger.

Fed by earlier layers

  1. L14:2627 excites 'or' or 'and' joining two items
  2. L3:1114 suppresses
  3. L7:669 weakly excites
  4. L13:2255 weakly suppresses
  5. L3:537 weakly suppresses
  6. L14:9 weakly suppresses
  7. L1:1624 weakly suppresses
  8. L7:1784 weakly excites punctuation right after 'of' or 'with'
  9. L10:2522 weakly excites
  10. L7:68 weakly suppresses
  11. L11:190 weakly excites
  12. L11:2877 weakly suppresses
  13. L14:5 weakly suppresses
  14. L6:1018 weakly suppresses
  15. L9:2244 weakly excites
  16. L11:519 weakly suppresses
  17. L13:2069 weakly suppresses
  18. L12:340 weakly suppresses
  19. L14:868 weakly suppresses
  20. L14:2249 weakly excites
  21. L2:36 weakly excites
  22. L11:2288 weakly excites
  23. L11:807 weakly suppresses
  24. L4:628 weakly suppresses

Feeds later layers

  1. L18:2703 excites
  2. L19:2327 excites
  3. L17:1679 excites
  4. L20:2454 weakly excites
  5. L17:2067 weakly excites
  6. L17:2017 weakly excites
  7. L25:477 weakly excites
  8. L18:2557 weakly excites
  9. L16:2537 weakly excites
  10. L18:2255 weakly excites
  11. L16:2912 weakly excites
  12. L21:1757 weakly excites
  13. L18:834 weakly excites
  14. L17:356 weakly excites
  15. L17:294 weakly excites
  16. L19:504 weakly excites
  17. L17:1886 weakly excites
  18. L24:55 weakly excites
  19. L23:1317 weakly excites
  20. L16:1192 weakly excites
  21. L22:793 weakly excites
  22. L21:621 weakly excites
  23. L16:247 weakly excites
  24. L25:1132 weakly excites

Activation histogram

How often this neuron fires at each strength. Almost always it does close to nothing (the tall bars in the middle); the snippets above are the rare moments it fired hard, amber for positive and blue for negative.

2 values between -1.58 and -1.184 values between -1.18 and -0.77128 values between -0.77 and -0.372066 values between -0.37 and 0.041602 values between 0.04 and 0.4472 values between 0.44 and 0.8510 values between 0.85 and 1.254 values between 1.25 and 1.654 values between 1.65 and 2.063 values between 2.06 and 2.463 values between 2.46 and 2.871 values between 2.87 and 3.272 values between 3.68 and 4.081 values between 4.08 and 4.491 values between 4.89 and 5.301 values between 6.51 and 6.911 values between 7.72 and 8.131 values between 8.13 and 8.531 values between 11.77 and 12.171 values between 14.20 and 14.60offnegativepositiveoften

Logit lens

The words this neuron nudges the model toward (amber) or away from (blue) when it fires. A hint, not a label: many neurons work through later layers instead.

Promotes

  1. 嗑
  2. 必备
  3. ilyn
  4. ursor
  5. inity
  6. ina
  7. iti
  8. 许
  9. ят
  10. /Input

Suppresses

  1. Wise
  2. いない
  3. xp
  4. 骢
  5. 端
  6. CastException
  7. anson
  8. urgeon
  9. 鼓
  10. XP